Distribution Network Load Forecasting Based on Deep Learning

Distribution Network Load Forecasting Based on Deep Learning

연구 분야: Artificial Intelligence

학회: IoTML '24: Proceedings of the 2024 4th International Conference on Internet of Things and Machine Learning

In order to improve the accuracy and robustness of load forecasting in distribution networks, a Long Short Term Memory (LSTM) model was constructed based on deep learning techniques. Design a multi-layer LSTM network architecture through correlation analysis and feature importance assessment, and improve the predictive performance of the model. The experimental results show that the LSTM model exhibits excellent accuracy in hourly, daily, and weekly predictions, significantly better than traditional ARIMA and Support Vector Regression (SVR) models, and maintains good robustness in noisy environments. This method provides effective technical support for the development of smart grids.